专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US10048826B2 Interactive visualizations of a convolutional neural network 有权
公开(公告)号：US10048826B2
公开(公告)日：2018-08-14
申请号：US15724029
申请日：2017-10-03
申请人： SAS Institute Inc. , North Carolina State University
发明人： Samuel Paul Leeman-Munk , Saratendu Sethi , Christopher Graham Healey , Shaoliang Nie , Kalpesh Padia , Ravinder Devarajan , David James Caira , Jordan Riley Benson , James Allen Cox , Lawrence E. Lewis , Mustafa Onur Kabul
IPC分类号： G06N3/04 , G06F3/0481 , G06F8/34 , G06T11/60 , G06N3/10
摘要： Interactive visualizations of a convolutional neural network are provided. For example, a graphical user interface (GUI) can include a matrix having symbols indicating feature-map values that represent likelihoods of particular features being present or absent at various locations in an input to a convolutional neural network. Each column in the matrix can have feature-map values generated by convolving the input to the convolutional neural network with a respective filter for identifying a particular feature in the input. The GUI can detect, via an input device, an interaction indicating that that the columns in the matrix are to be combined into a particular number of groups. Based on the interaction, the columns can be clustered into the particular number of groups using a clustering method. The matrix in the GUI can then be updated to visually represent each respective group of columns as a single column of symbols within the matrix.

2. 发明申请

US20180211153A1 PATTERN IDENTIFIER SYSTEM 审中-公开
公开(公告)号：US20180211153A1
公开(公告)日：2018-07-26
申请号：US15658566
申请日：2017-07-25
申请人： SAS Institute Inc.
发明人： Stuart Andrew Hunt , Samuel Paul Leeman-Munk , Richard Welland Crowell
IPC分类号： G06N3/04 , G06N5/04 , G06N3/08
CPC分类号： G06N3/0445 , G06N3/0454 , G06N3/049 , G06N3/08 , G06N3/084 , G06N5/047
摘要： A computing device identifies a pattern in a dataset. A first neural network model is executed using data points as input to input nodes of the first neural network model to generate first output node data. A second neural network model is executed using the first output node data as input to input nodes of the second neural network model to generate second output node data. The second output node data includes a plurality of output values for each x-value of the plurality of data points. For each x-value, an output value of the plurality of output values is associated with a single pattern type of a plurality of predefined pattern types. For each pattern type of the plurality of predefined pattern types, a start time and a stop time is identified when the output value for the associated pattern type exceeds a predefined pattern window threshold value.

3. 发明授权

US10235622B2 Pattern identifier system 有权
公开(公告)号：US10235622B2
公开(公告)日：2019-03-19
申请号：US15658566
申请日：2017-07-25
申请人： SAS Institute Inc.
发明人： Stuart Andrew Hunt , Samuel Paul Leeman-Munk , Richard Welland Crowell
IPC分类号： G06N3/04 , G06N3/08 , G06N5/04
摘要： A computing device identifies a pattern in a dataset. A first neural network model is executed using data points as input to input nodes of the first neural network model to generate first output node data. A second neural network model is executed using the first output node data as input to input nodes of the second neural network model to generate second output node data. The second output node data includes a plurality of output values for each x-value of the plurality of data points. For each x-value, an output value of the plurality of output values is associated with a single pattern type of a plurality of predefined pattern types. For each pattern type of the plurality of predefined pattern types, a start time and a stop time is identified when the output value for the associated pattern type exceeds a predefined pattern window threshold value.

4. 发明授权

US09934462B1 Visualizing deep neural networks 有权
公开(公告)号：US09934462B1
公开(公告)日：2018-04-03
申请号：US15584984
申请日：2017-05-02
申请人： SAS Institute Inc. , North Carolina State University
发明人： Christopher Graham Healey , Samuel Paul Leeman-Munk , Shaoliang Nie , Kalpesh Padia , Ravinder Devarajan , David James Caira , Jordan Riley Benson , Saratendu Sethi , James Allen Cox , Lawrence E. Lewis
IPC分类号： G06N3/04 , G06N3/10
CPC分类号： G06N3/04 , G06N3/105
摘要： Deep neural networks can be visualized. For example, first values for a first layer of nodes in a neural network, second values for a second layer of nodes in the neural network, and/or third values for connections between the first layer of nodes and the second layer of nodes can be received. A quilt graph can be output that includes (i) a first set of symbols having visual characteristics representative of the first values and representing the first layer of nodes along a first axis; (ii) a second set of symbols having visual characteristics representative of the second values and representing the second layer of nodes along a second axis; and/or (iii) a matrix of blocks between the first axis and the second axis having visual characteristics representative of the third values and representing the connections between the first layer of nodes and the second layer of nodes.

5. 发明申请

US20160350650A1 NORMALIZING ELECTRONIC COMMUNICATIONS USING NEURAL NETWORKS 有权
标题翻译：使用神经网络正规化电子通信
公开(公告)号：US20160350650A1
公开(公告)日：2016-12-01
申请号：US14937810
申请日：2015-11-10
申请人： SAS Institute Inc. , North Carolina State University
发明人： Samuel Paul Leeman-Munk , Wookhee Min , Bradford Wayne Mott , James Curtis Lester, II , James Allen Cox
IPC分类号： G06N3/08 , G06N3/04
CPC分类号： G06N3/08 , G06F17/273 , G06F17/2785 , G06N3/04 , G06N3/0454 , H04L51/063
摘要： Electronic communications can be normalized using neural networks. For example, an electronic representation of a noncanonical communication can be received. A normalized version of the noncanonical communication can be determined using a normalizer including a neural network. The neural network can receive a single vector at an input layer of the neural network and transform an output of a hidden layer of the neural network into multiple values that sum to a total value of one. Each value of the multiple values can be a number between zero and one and represent a probability of a particular character being in a particular position in the normalized version of the noncanonical communication. The neural network can determine the normalized version of the noncanonical communication based on the multiple values. Whether the normalized version should be output can be determined based on a result from a flagger including another neural network.
摘要翻译：电子通信可以使用神经网络进行归一化。例如，可以接收非经典通信的电子表示。非规范通信的归一化版本可以使用包括神经网络的规范化器来确定。神经网络可以在神经网络的输入层处接收单个向量，并将神经网络的隐层的输出转换为总和为1的多个值。多个值的每个值可以是零和一之间的数字，并且表示特定字符在非规范通信的归一化版本中处于特定位置的概率。神经网络可以基于多个值来确定非经典通信的归一化版本。是否应该输出归一化版本可以基于包括另一个神经网络的标志符的结果来确定。

6. 发明授权

US11501084B1 Graphical user interface for visualizing contributing factors to a machine-learning model's output 有权
公开(公告)号：US11501084B1
公开(公告)日：2022-11-15
申请号：US17747139
申请日：2022-05-18
申请人： SAS Institute Inc.
发明人： Reza Soleimani , Samuel Paul Leeman-Munk , James Allen Cox , David Blake Styles
IPC分类号： G06F40/30 , G06F40/284 , G06F40/205 , G06N20/20
摘要： In one example, a system can execute a first machine-learning model to determine an overall classification for a textual dataset. The system can also determine classification scores indicating the level of influence that each token in the textual dataset had on the overall classification. The system can select a first subset of the tokens based on their classification scores. The system can also execute a second machine-learning model to determine probabilities that the textual dataset falls into various categories. The system can determine category scores indicating the level of influence that each token had on a most-likely category determination. The system can select a second subset of the tokens based on their category scores. The system can then generate a first visualization depicting the first subset of tokens color-coded to indicate their classification scores and a second visualization depicting the second subset of tokens color-coded to indicate their category scores.

7. 发明授权

US10324983B2 Interactive visualizations for a recurrent neural network 有权
公开(公告)号：US10324983B2
公开(公告)日：2019-06-18
申请号：US16138446
申请日：2018-09-21
申请人： SAS Institute Inc. , North Carolina State University
发明人： Samuel Paul Leeman-Munk , Saratendu Sethi , Christopher Graham Healey , Shaoliang Nie , Kalpesh Padia , Ravinder Devarajan , David James Caira , Jordan Riley Benson , James Allen Cox , Lawrence E. Lewis
IPC分类号： G06N3/10 , G06F16/904 , G06F3/0484 , G06N3/04 , G06K9/62 , G06F3/0481
摘要： Recurrent neural networks (RNNs) can be visualized. For example, a processor can receive vectors indicating values of nodes in a gate of a RNN. The values can result from processing data at the gate during a sequence of time steps. The processor can group the nodes into clusters by applying a clustering method to the values of the nodes. The processor can generate a first graphical element visually indicating how the respective values of the nodes in a cluster changed during the sequence of time steps. The processor can also determine a reference value based on multiple values for multiple nodes in the cluster, and generate a second graphical element visually representing how the respective values of the nodes in the cluster each relate to the reference value. The processor can cause a display to output a graphical user interface having the first graphical element and the second graphical element.

8. 发明授权

US09552547B2 Normalizing electronic communications using a neural-network normalizer and a neural-network flagger 有权
标题翻译：使用神经网络规范化器和神经网络标志器来归一化电子通信
公开(公告)号：US09552547B2
公开(公告)日：2017-01-24
申请号：US14937810
申请日：2015-11-10
申请人： SAS Institute Inc. , North Carolina State University
发明人： Samuel Paul Leeman-Munk , Wookhee Min , Bradford Wayne Mott , James Curtis Lester, II , James Allen Cox
IPC分类号： G06N3/08 , G06N3/04
CPC分类号： G06N3/08 , G06F17/273 , G06F17/2785 , G06N3/04 , G06N3/0454 , H04L51/063
摘要： Electronic communications can be normalized using neural networks. For example, an electronic representation of a noncanonical communication can be received. A normalized version of the noncanonical communication can be determined using a normalizer including a neural network. The neural network can receive a single vector at an input layer of the neural network and transform an output of a hidden layer of the neural network into multiple values that sum to a total value of one. Each value of the multiple values can be a number between zero and one and represent a probability of a particular character being in a particular position in the normalized version of the noncanonical communication. The neural network can determine the normalized version of the noncanonical communication based on the multiple values. Whether the normalized version should be output can be determined based on a result from a flagger including another neural network.
摘要翻译：电子通信可以使用神经网络进行归一化。例如，可以接收非经典通信的电子表示。非规范通信的归一化版本可以使用包括神经网络的规范化器来确定。神经网络可以在神经网络的输入层处接收单个向量，并将神经网络的隐层的输出转换为总和为1的多个值。多个值的每个值可以是零和一之间的数字，并且表示特定字符在非规范通信的归一化版本中处于特定位置的概率。神经网络可以基于多个值来确定非经典通信的归一化版本。是否应该输出归一化版本可以基于包括另一个神经网络的标志符的结果来确定。

9. 发明授权

US10191921B1 System for expanding image search using attributes and associations 有权
公开(公告)号：US10191921B1
公开(公告)日：2019-01-29
申请号：US15944163
申请日：2018-04-03
申请人： SAS Institute Inc.
发明人： Ethem F. Can , Richard Welland Crowell , Samuel Paul Leeman-Munk , Jared Peterson , Saratendu Sethi
IPC分类号： G06F17/30 , G06N3/08
摘要： A system provides image search results based on a query that includes an attribute or an association and a concept identifier. The query is input into a trained query model to define a search syntax for the query. The search syntax is submitted to an expanded annotated image database that includes a concept image of a concept identified by the concept identifier with a plurality of attributes associated with the concept and a plurality of associations associated with the concept. A query result is received based on matching the defined search syntax to one or more of the attributes or one or more of the associations. The query result includes the concept image of the concept associated with the matched one or more of the attributes or one or more of the associations. The concept image included in the received query result is presented in a display.

10. 发明授权

US09595002B2 Normalizing electronic communications using a vector having a repeating substring as input for a neural network 有权
标题翻译：使用具有重复子串的向量作为神经网络的输入来归一化电子通信
公开(公告)号：US09595002B2
公开(公告)日：2017-03-14
申请号：US15175503
申请日：2016-06-07
申请人： SAS Institute Inc.
发明人： Samuel Paul Leeman-Munk , James Allen Cox
IPC分类号： G06N3/04 , H04W4/00
CPC分类号： G06N3/0445 , G06N3/0454 , G06N3/0472
摘要： Electronic communications can be normalized using a neural network. For example, a noncanonical communication that includes multiple terms can be received. The noncanonical communication can be preprocessed by (I) generating a vector including multiple characters from a term of the multiple terms; and (II) repeating a substring of the term in the vector such that a last character of the substring is positioned in a last position in the vector. The vector can be transmitted to a neural network configured to receive the vector and generate multiple probabilities based on the vector. A normalized version of the noncanonical communication can be determined using one or more of the multiple probabilities generated by the neural network. Whether the normalized version of the noncanonical communication should be outputted can also be determined using at least one of the multiple probabilities generated by the neural network.
摘要翻译：电子通信可以使用神经网络进行归一化。例如，可以接收包括多个术语的非经典通信。非经典通信可以通过（I）从多个术语的术语生成包括多个字符的向量来预处理; 和（II）在向量中重复该项的子串，使得子串的最后一个字符位于向量中的最后位置。向量可以被传送到被配置为接收向量并且基于向量生成多个概率的神经网络。可以使用由神经网络生成的多个概率中的一个或多个来确定非规范通信的归一化版本。还可以使用神经网络生成的多个概率中的至少一个来确定是否应该输出非规范通信的归一化版本。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式